{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6EXQ3SQF5RNC6VEDJ3DVJHILOG","short_pith_number":"pith:6EXQ3SQF","schema_version":"1.0","canonical_sha256":"f12f0dca05ec5a2f54834ec7549d0b719cf10829846fbfa8c326d11106e151ae","source":{"kind":"arxiv","id":"2505.18366","version":1},"attestation_state":"computed","paper":{"title":"Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amit Agarwal, Hansa Meghwani, Hitesh Laxmichand Patel, Priyaranjan Pattnayak, Srikant Panda","submitted_at":"2025-05-23T20:51:20Z","abstract_excerpt":"Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge management, customer support, and retrieval-augmented generation agents. To address this challenge, we propose a scalable hard-negative mining framework tailored specifically for domain-specific enterprise data. Our approach dynamically selects semantically challenging but contextually irrelevant documents to enhance deployed re-ranking models.\n  Our method integ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.18366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T20:51:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"63dd3cfcaba3da186a27430f30a65b6954effeb0b8228eeaadd00336c171cae4","abstract_canon_sha256":"4b085c1d14100ccc47063a7ab8baa975d48d7cd0743d859d12a76aff3d469cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:45.441502Z","signature_b64":"5inDaKRZyF/FmaviB9ToazsBNiFXn4S2Zh+BnGYoZD4s1Logn6cmW8eT5dlMWOy1ZKmevVGrC8s1Ut5OEotTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f12f0dca05ec5a2f54834ec7549d0b719cf10829846fbfa8c326d11106e151ae","last_reissued_at":"2026-07-05T11:08:45.441058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:45.441058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amit Agarwal, Hansa Meghwani, Hitesh Laxmichand Patel, Priyaranjan Pattnayak, Srikant Panda","submitted_at":"2025-05-23T20:51:20Z","abstract_excerpt":"Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge management, customer support, and retrieval-augmented generation agents. To address this challenge, we propose a scalable hard-negative mining framework tailored specifically for domain-specific enterprise data. Our approach dynamically selects semantically challenging but contextually irrelevant documents to enhance deployed re-ranking models.\n  Our method integ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18366","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18366/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.18366","created_at":"2026-07-05T11:08:45.441115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18366v1","created_at":"2026-07-05T11:08:45.441115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18366","created_at":"2026-07-05T11:08:45.441115+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EXQ3SQF5RNC","created_at":"2026-07-05T11:08:45.441115+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EXQ3SQF5RNC6VED","created_at":"2026-07-05T11:08:45.441115+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EXQ3SQF","created_at":"2026-07-05T11:08:45.441115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02097","citing_title":"Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG","json":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG.json","graph_json":"https://pith.science/api/pith-number/6EXQ3SQF5RNC6VEDJ3DVJHILOG/graph.json","events_json":"https://pith.science/api/pith-number/6EXQ3SQF5RNC6VEDJ3DVJHILOG/events.json","paper":"https://pith.science/paper/6EXQ3SQF"},"agent_actions":{"view_html":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG","download_json":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG.json","view_paper":"https://pith.science/paper/6EXQ3SQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18366&json=true","fetch_graph":"https://pith.science/api/pith-number/6EXQ3SQF5RNC6VEDJ3DVJHILOG/graph.json","fetch_events":"https://pith.science/api/pith-number/6EXQ3SQF5RNC6VEDJ3DVJHILOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG/action/storage_attestation","attest_author":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG/action/author_attestation","sign_citation":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG/action/citation_signature","submit_replication":"https://pith.science/pith/6EXQ3SQF5RNC6VEDJ3DVJHILOG/action/replication_record"}},"created_at":"2026-07-05T11:08:45.441115+00:00","updated_at":"2026-07-05T11:08:45.441115+00:00"}